Land or Water? (Celeste): leaderboard
Earth reconstruction from geographic knowledge: Celeste (@celestepoasts) asks twelve Claude models whether each of 16,200 latitude/longitude coordinates on a 2-degree grid is land or water, without images or tools. The score is area-weighted accuracy against a 1-km land mask, on a 0–100% scale; higher is better. These are the September 24, 2026 chart results. Fable 5, Fable 5.1 and Opus 5.5 use low-effort thinking; other run settings are unspecified. Exact prompts, the reference mask and per-point answers were not available for independent verification.
Metric: Area-weighted accuracy (%). Source: x.com. Saturation forecast: Estimated already saturated. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5.5 (Low) | 99 |
| 2 | Claude Fable 5.1 (Low) | 98.2 |
| 3 | Claude Fable 5 (Low) | 97.8 |
| 4 | Claude Opus 5 | 92.5 |
| 5 | Claude Opus 4.8 | 91.7 |
| 6 | Claude Sonnet 5 | 91.5 |
| 7 | Claude Opus 4.6 | 91.2 |
| 8 | Claude Opus 4.7 | 91.2 |
| 9 | Claude Sonnet 4.6 | 89.1 |
| 10 | Claude Opus 4.5 | 82.6 |
| 11 | Claude Haiku 4.5 | 81.3 |
| 12 | Claude Sonnet 4.5 | 60.5 |
Interactive version: theaggregate.ai/benchmark?slug=land-or-water-celeste · How It Works · Data refreshed daily, snapshot 2026-10-09.